Genetically Optimized Prediction of Remaining Useful Life

TL;DR

This paper introduces a genetically optimized neural network architecture for remaining useful life prediction, enhancing prediction consistency and hyper-parameter tuning over traditional deep learning models.

Contribution

It proposes a novel genetic algorithm-based optimization method for hyper-parameters in RUL prediction models, improving prediction accuracy and robustness.

Findings

Genetically optimized models outperform standard LSTM and GRU.

Hyper-parameter optimization enhances prediction accuracy.

The approach demonstrates superior results on NASA Turbofan dataset.

Abstract

The application of remaining useful life (RUL) prediction has taken great importance in terms of energy optimization, cost-effectiveness, and risk mitigation. The existing RUL prediction algorithms mostly constitute deep learning frameworks. In this paper, we implement LSTM and GRU models and compare the obtained results with a proposed genetically trained neural network. The current models solely depend on Adam and SGD for optimization and learning. Although the models have worked well with these optimizers, even little uncertainties in prognostics prediction can result in huge losses. We hope to improve the consistency of the predictions by adding another layer of optimization using Genetic Algorithms. The hyper-parameters - learning rate and batch size are optimized beyond manual capacity. These models and the proposed architecture are tested on the NASA Turbofan Jet Engine dataset. The optimized architecture can predict the given hyper-parameters autonomously and provide superior results.